List your company

Tool-Use Agent Evaluation on BFCL Multiturn (OOD) v3 (test)

48Base RateTopoCurate-RL
2.2414.122637.88Mar 2, 2026

Evaluation results

MethodLinks
TopoCurate-RLModel Size=32B, Strategy=RL, Topology Modeling=Enabled2026.034829.522.532.5
TopoCurate-RL (w/o Topology)Model Size=32B, Strategy=RL, Topology Modeling=Disabled2026.034524.516.526
TopoCurate-SFTModel Size=32B, Strategy=SFT, Topology Modeling=Enabled2026.034326.513.529.5
MUA-RLModel Size=32B, Strategy=RL2026.034221.52030
TopoCurate-SFT (w/o Topology)Model Size=32B, Strategy=SFT, Topology Modeling=Disabled2026.034123.512.524.5
APIGen-MT-SFTModel Size=32B, Strategy=SFT2026.0337.521.517.520.5
MUA-SFTModel Size=32B, Strategy=SFT2026.033519.52128.5
Qwen3-32B-ThinkingModel Size=32B, Strategy=Thinking2026.03342115.524.5
TopoCurate-RLModel Size=8B, Strategy=RL, Topology Modeling=Enabled2026.0329.51613.518
TopoCurate-SFT (w/o Topology)Model Size=8B, Strategy=SFT, Topology Modeling=Disabled2026.0326.513.57.515
TopoCurate-SFTModel Size=8B, Strategy=SFT, Topology Modeling=Enabled2026.0326.512.5916
TopoCurate-RL (w/o Topology)Model Size=8B, Strategy=RL, Topology Modeling=Disabled2026.0325.514.510.516
APIGen-MT-SFTModel Size=8B, Strategy=SFT2026.0324.514517
MUA-SFTModel Size=8B, Strategy=SFT2026.0324101116.5
Qwen3-8B-ThinkingModel Size=8B, Strategy=Thinking2026.032313.54.513.5
MUA-RLModel Size=8B, Strategy=RL2026.03211111.515
Simia-Tau-SFTModel Size=8B, Strategy=SFT2026.034.520.58
Simia-Tau-RLModel Size=8B, Strategy=RL2026.0342.51.57.5